© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110741
    Prev
    Next
    INDEX
    Explanations

    dot products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    การ
    -0.08
     bron
    -0.08
    无需
    -0.08
     dosing
    -0.07
     demographic
    -0.07
     Server
    -0.07
     retrofit
    -0.07
    (Value
    -0.07
     exemptions
    -0.07
    adhan
    -0.07
    POSITIVE LOGITS
     FVector
    0.09
     INNER
    0.09
    [list
    0.09
    Dot
    0.08
    obi
    0.08
     astore
    0.08
    ің
    0.08
    .inner
    0.08
    _vectors
    0.08
    attrib
    0.08
    Activations Density 0.019%

    No Known Activations